Unicode Character Functions

Enumerations
enum	BIDIFLAGS { BIDIFLAG_L = (1 << BIDITAG_L), BIDIFLAG_LRE = (1 << BIDITAG_LRE), BIDIFLAG_LRO = (1 << BIDITAG_LRO), BIDIFLAG_R = (1 << BIDITAG_R), BIDIFLAG_AL = (1 << BIDITAG_AL), BIDIFLAG_RLE = (1 << BIDITAG_RLE), BIDIFLAG_RLO = (1 << BIDITAG_RLO), BIDIFLAG_PDF = (1 << BIDITAG_PDF), BIDIFLAG_EN = (1 << BIDITAG_EN), BIDIFLAG_ES = (1 << BIDITAG_ES), BIDIFLAG_ET = (1 << BIDITAG_ET), BIDIFLAG_AN = (1 << BIDITAG_AN), BIDIFLAG_CS = (1 << BIDITAG_CS), BIDIFLAG_NSM = (1 << BIDITAG_NSM), BIDIFLAG_BN = (1 << BIDITAG_BN), BIDIFLAG_B = (1 << BIDITAG_B), BIDIFLAG_WS = (1 << BIDITAG_WS), BIDIFLAG_ON = (1 << BIDITAG_ON) }
enum	BIDITAG { BIDITAG_L = 0, BIDITAG_LRE = 1, BIDITAG_LRO = 2, BIDITAG_R = 3, BIDITAG_AL = 4, BIDITAG_RLE = 5, BIDITAG_RLO = 6, BIDITAG_PDF = 7, BIDITAG_EN = 8, BIDITAG_ES = 9, BIDITAG_ET = 10, BIDITAG_AN = 11, BIDITAG_CS = 12, BIDITAG_NSM = 13, BIDITAG_BN = 14, BIDITAG_B = 15, BIDITAG_WS = 16, BIDITAG_ON = 17 }
enum	UCCAT { UCCAT_Cn = 0, UCCAT_Lu = 1, UCCAT_Ll = 2, UCCAT_Lt = 3, UCCAT_Lm = 4, UCCAT_Lo = 5, UCCAT_Mn = 6, UCCAT_Mc = 7, UCCAT_Me = 8, UCCAT_Nd = 9, UCCAT_Nl = 10, UCCAT_No = 11, UCCAT_Zs = 12, UCCAT_Zl = 13, UCCAT_Zp = 14, UCCAT_Cc = 15, UCCAT_Cf = 16, UCCAT_Cs = 17, UCCAT_Co = 18, UCCAT_Pc = 20, UCCAT_Pd = 21, UCCAT_Ps = 22, UCCAT_Pe = 23, UCCAT_Pi = 24, UCCAT_Pf = 25, UCCAT_Po = 26, UCCAT_Sm = 27, UCCAT_Sc = 28, UCCAT_Sk = 29, UCCAT_So = 30 }
enum	UCCATFLAGS { UCCATFLAG_Cn = (1 << UCCAT_Cn), UCCATFLAG_Lu = (1 << UCCAT_Lu), UCCATFLAG_Ll = (1 << UCCAT_Ll), UCCATFLAG_Lt = (1 << UCCAT_Lt), UCCATFLAG_Lm = (1 << UCCAT_Lm), UCCATFLAG_Lo = (1 << UCCAT_Lo), UCCATFLAG_Mn = (1 << UCCAT_Mn), UCCATFLAG_Mc = (1 << UCCAT_Mc), UCCATFLAG_Me = (1 << UCCAT_Me), UCCATFLAG_Nd = (1 << UCCAT_Nd), UCCATFLAG_Nl = (1 << UCCAT_Nl), UCCATFLAG_No = (1 << UCCAT_No), UCCATFLAG_Zs = (1 << UCCAT_Zs), UCCATFLAG_Zl = (1 << UCCAT_Zl), UCCATFLAG_Zp = (1 << UCCAT_Zp), UCCATFLAG_Cc = (1 << UCCAT_Cc), UCCATFLAG_Cf = (1 << UCCAT_Cf), UCCATFLAG_Cs = (1 << UCCAT_Cs), UCCATFLAG_Co = (1 << UCCAT_Co), UCCATFLAG_Pc = (1 << UCCAT_Pc), UCCATFLAG_Pd = (1 << UCCAT_Pd), UCCATFLAG_Ps = (1 << UCCAT_Ps), UCCATFLAG_Pe = (1 << UCCAT_Pe), UCCATFLAG_Pi = (1 << UCCAT_Pi), UCCATFLAG_Pf = (1 << UCCAT_Pf), UCCATFLAG_Po = (1 << UCCAT_Po), UCCATFLAG_Sm = (1 << UCCAT_Sm), UCCATFLAG_Sc = (1 << UCCAT_Sc), UCCATFLAG_Sk = (1 << UCCAT_Sk), UCCATFLAG_So = (1 << UCCAT_So), UCCATFLAG_Mi = (1 << 31) }
Functions
bool	ucisalnum (MIUNICODE c)
bool	ucisalpha (MIUNICODE c)
LIBEXPORT bool	ucisbidiprop (MIUNICODE c, UINT32 bidiflags)
bool	ucisblank (MIUNICODE c)
bool	ucisclosepunct (MIUNICODE c)
bool	uciscntrl (MIUNICODE c)
bool	ucisconnect (MIUNICODE c)
bool	uciscurrency (MIUNICODE c)
bool	ucisdash (MIUNICODE c)
LIBEXPORT bool	ucisdecompbidiprop (MIUNICODE c, UINT32 decompflags)
bool	ucisdigit0to9 (MIUNICODE c)
bool	ucisdigit2 (MIUNICODE c)
bool	ucisenclosing (MIUNICODE c)
bool	ucisfinalpunct (MIUNICODE c)
bool	ucisfmtcntrl (MIUNICODE c)
bool	ucishan (MIUNICODE c)
bool	ucishangul (MIUNICODE c)
bool	ucisinitialpunct (MIUNICODE c)
bool	ucisisocntrl (MIUNICODE c)
bool	ucislower (MIUNICODE c)
bool	ucislsep (MIUNICODE c)
bool	ucisltr (MIUNICODE c)
bool	ucismark (MIUNICODE c)
bool	ucismath (MIUNICODE c)
bool	ucismodif (MIUNICODE c)
bool	ucismodifsymbol (MIUNICODE c)
bool	ucisneutral (MIUNICODE c)
bool	ucisnonspacing (MIUNICODE c)
bool	ucisnsmark (MIUNICODE c)
bool	ucisnumber (MIUNICODE c)
bool	ucisopenpunct (MIUNICODE c)
LIBEXPORT bool	ucisprop (MIUNICODE c, UINT32 uccatflags)
bool	ucispsep (MIUNICODE c)
bool	ucispunct (MIUNICODE c)
bool	ucisrtl (MIUNICODE c)
bool	ucisspace (MIUNICODE c)
bool	ucisspmark (MIUNICODE c)
bool	ucisstrong (MIUNICODE c)
bool	ucissymbol (MIUNICODE c)
bool	ucistitle (MIUNICODE c)
bool	ucisupper (MIUNICODE c)
bool	ucisweak (MIUNICODE c)
LIBEXPORT MIUNICODE	uctolower (MIUNICODE c)
LIBEXPORT MIUNICODE	uctoupper (MIUNICODE c)

Enumeration Type Documentation

enum BIDIFLAGS

Flags for the above which can be ORd together.

Enumerator:

BIDIFLAG_L
BIDIFLAG_LRE	Left-to-right.
BIDIFLAG_LRO	Left-to-right Embedding.
BIDIFLAG_R	Left-to-right Override.
BIDIFLAG_AL	Right-to-left.
BIDIFLAG_RLE	Right-to-left arabic.
BIDIFLAG_RLO	Right-to-left embedding.
BIDIFLAG_PDF	Right-to-left override.
BIDIFLAG_EN	Pop Directional Format.
BIDIFLAG_ES	European Number.
BIDIFLAG_ET	European Number separator.
BIDIFLAG_AN	European Number Terminator.
BIDIFLAG_CS	Arabic Number.
BIDIFLAG_NSM	Common Number Separator.
BIDIFLAG_BN	Non Spacing Mark.
BIDIFLAG_B	Boundary Neutral.
BIDIFLAG_WS	Paragraph Separator.
BIDIFLAG_ON	White Space.

enum BIDITAG

Unicode Bidirectional category from column 4 of UnicodeData.txt See details on UCCATEGORY enum above.

These are summarized in chapter 3 of the Unicode Standard

Enumerator:

BIDITAG_L	Left-to-right.
BIDITAG_LRE	Left-to-right Embedding.
BIDITAG_LRO	Left-to-right Override.
BIDITAG_R	Right-to-left.
BIDITAG_AL	Right-to-left arabic.
BIDITAG_RLE	Right-to-left embedding.
BIDITAG_RLO	Right-to-left override.
BIDITAG_PDF	Pop Directional Format.
BIDITAG_EN	European Number.
BIDITAG_ES	European Number separator.
BIDITAG_ET	European Number Terminator.
BIDITAG_AN	Arabic Number.
BIDITAG_CS	Common Number Separator.
BIDITAG_NSM	Non Spacing Mark.
BIDITAG_BN	Boundary Neutral.
BIDITAG_B	Paragraph Separator.
BIDITAG_WS	White Space.
BIDITAG_ON	Other Neutrals.

enum UCCAT

These are the general category codes from column 2 of the UnicodeData.txt.

The numbers are arbitrarily assigned by me. UnicodeData.txt has the 2-letter codes. You may be asking why I defined the values for all the enums when the compiler would do that for me...See, this way it would be a pain to insert something into the middle and renumber them, wouldn't it? Good! don't do that. ucdata.ref has the numbers and if you renumber them, you'll break things.

Enumerator:

UCCAT_Cn	Other , Not assigned (norm).
UCCAT_Lu	Letter, Uppercase (norm).
UCCAT_Ll	Letter, Lowercase (norm).
UCCAT_Lt	Letter, Titlecase (norm).
UCCAT_Lm	Letter, Modifier.
UCCAT_Lo	Letter, Other.
UCCAT_Mn	Mark, non-spacing (norm).
UCCAT_Mc	Mark, spacing combining (norm).
UCCAT_Me	Mark, encolsing (norm).
UCCAT_Nd	Number Decimal digit (norm).
UCCAT_Nl	Number Letter (norm).
UCCAT_No	Number Other (norm).
UCCAT_Zs	Separator, space (norm).
UCCAT_Zl	Separator, line (norm).
UCCAT_Zp	Separator, paragraph (norm).
UCCAT_Cc	Other , control (norm).
UCCAT_Cf	Other , format (norm).
UCCAT_Cs	Other , surrogate (norm).
UCCAT_Co	Other , Private use (norm).
UCCAT_Pc	Punctuation, connector.
UCCAT_Pd	Punctuation, Dash.
UCCAT_Ps	Punctuation, Open.
UCCAT_Pe	Punctuation, Close.
UCCAT_Pi	Punctuation, Initial quote.
UCCAT_Pf	Punctuation, final quote.
UCCAT_Po	Punctuation, other.
UCCAT_Sm	Symbol, math.
UCCAT_Sc	Symbol, currency.
UCCAT_Sk	Symbol, modifier.
UCCAT_So	Symbol, other.

enum UCCATFLAGS

Flags for the above which can be ORd together.

Enumerator:

UCCATFLAG_Cn
UCCATFLAG_Lu	Other , Not assigned (norm).
UCCATFLAG_Ll	Letter, Uppercase (norm).
UCCATFLAG_Lt	Letter, Lowercase (norm).
UCCATFLAG_Lm	Letter, Titlecase (norm).
UCCATFLAG_Lo	Letter, Modifier.
UCCATFLAG_Mn	Letter, Other.
UCCATFLAG_Mc	Mark, non-spacing (norm).
UCCATFLAG_Me	Mark, spacing combining (norm).
UCCATFLAG_Nd	Mark, encolsing (norm).
UCCATFLAG_Nl	Number Decimal digit (norm).
UCCATFLAG_No	Number Letter (norm).
UCCATFLAG_Zs	Number Other (norm).
UCCATFLAG_Zl	Separator, space (norm).
UCCATFLAG_Zp	Separator, line (norm).
UCCATFLAG_Cc	Separator, paragraph (norm).
UCCATFLAG_Cf	Other , control (norm).
UCCATFLAG_Cs	Other , format (norm).
UCCATFLAG_Co	Other , surrogate (norm).
UCCATFLAG_Pc	Other , Private use (norm).
UCCATFLAG_Pd	Punctuation, connector.
UCCATFLAG_Ps	Punctuation, Dash.
UCCATFLAG_Pe	Punctuation, Open.
UCCATFLAG_Pi	Punctuation, Close.
UCCATFLAG_Pf	Punctuation, Initial quote.
UCCATFLAG_Po	Punctuation, final quote.
UCCATFLAG_Sm	Punctuation, other.
UCCATFLAG_Sc	Symbol, math.
UCCATFLAG_Sk	Symbol, currency.
UCCATFLAG_So	Symbol, modifier.
UCCATFLAG_Mi	other

Function Documentation

bool ucisalnum ( MIUNICODE c ) [inline]

Alpha or Digit.

bool ucisalpha ( MIUNICODE c ) [inline]

Alpha.

LIBEXPORT bool ucisbidiprop	(	MIUNICODE	c,
		UINT32	bidiflags
	)

bool ucisblank ( MIUNICODE c ) [inline]

Space.

bool ucisclosepunct ( MIUNICODE c ) [inline]

Punctuation, Close.

bool uciscntrl ( MIUNICODE c ) [inline]

Control.

bool ucisconnect ( MIUNICODE c ) [inline]

Punctuation, Connecting.

bool uciscurrency ( MIUNICODE c ) [inline]

Symbol, Currency.

bool ucisdash ( MIUNICODE c ) [inline]

Punctuation, Dash.

LIBEXPORT bool ucisdecompbidiprop	(	MIUNICODE	c,
		UINT32	decompflags
	)

bool ucisdigit0to9 ( MIUNICODE c ) [inline]

Determine if digit 0 to 9.

bool ucisdigit2 ( MIUNICODE c ) [inline]

Digit (any digit, not just 0-9).

bool ucisenclosing ( MIUNICODE c ) [inline]

Mark, enclosing.

bool ucisfinalpunct ( MIUNICODE c ) [inline]

Punctuation, Final.

bool ucisfmtcntrl ( MIUNICODE c ) [inline]

bool ucishan ( MIUNICODE c ) [inline]

Han glyph.

bool ucishangul ( MIUNICODE c ) [inline]

Hangul glyph.

bool ucisinitialpunct ( MIUNICODE c ) [inline]

Punctuation, Initial.

bool ucisisocntrl ( MIUNICODE c ) [inline]

bool ucislower ( MIUNICODE c ) [inline]

bool ucislsep ( MIUNICODE c ) [inline]

Seperator, Line.

bool ucisltr ( MIUNICODE c ) [inline]

Strong Left-to-Right Directionality.

bool ucismark ( MIUNICODE c ) [inline]

Mark (any).

bool ucismath ( MIUNICODE c ) [inline]

Symbol, math.

bool ucismodif ( MIUNICODE c ) [inline]

Letter, modifier.

bool ucismodifsymbol ( MIUNICODE c ) [inline]

Symbol, modifier.

bool ucisneutral ( MIUNICODE c ) [inline]

Netutral Directionality.

bool ucisnonspacing ( MIUNICODE c ) [inline]

Mark, Non spacing.

bool ucisnsmark ( MIUNICODE c ) [inline]

Mark, non-spacing.

bool ucisnumber ( MIUNICODE c ) [inline]

Number (digit, letter form, other).

bool ucisopenpunct ( MIUNICODE c ) [inline]

Punctuation, Open.

LIBEXPORT bool ucisprop	(	MIUNICODE	c,
		UINT32	uccatflags
	)

Determine of a Unicode character has a given property.

The property flags are listed in ucstring.h. (the name is derived from isprop() from ctype.h) There are two sets of flags because there are so many possibilites with Unicode. You won't usually use this function directly.

bool ucispsep ( MIUNICODE c ) [inline]

Seperator, Paragraph.

bool ucispunct ( MIUNICODE c ) [inline]

bool ucisrtl ( MIUNICODE c ) [inline]

Strong Right-to-Left Directionality.

bool ucisspace ( MIUNICODE c ) [inline]

Space.

bool ucisspmark ( MIUNICODE c ) [inline]

Mark, spacing.

bool ucisstrong ( MIUNICODE c ) [inline]

Strong R-to-L or L-to-R Directionality.

bool ucissymbol ( MIUNICODE c ) [inline]

bool ucistitle ( MIUNICODE c ) [inline]

bool ucisupper ( MIUNICODE c ) [inline]

bool ucisweak ( MIUNICODE c ) [inline]

Weak Directionality.

LIBEXPORT MIUNICODE uctolower ( MIUNICODE c )

LIBEXPORT MIUNICODE uctoupper ( MIUNICODE c )

Unicode Character Functions

Enumerations

Functions

Enumeration Type Documentation

Function Documentation